© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19339
    Prev
    Next
    INDEX
    Explanations

    numbers and votes

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is primarily detecting multi‐digit numerical figures (e.g. vote tallies, percentages, or other large numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </u>
    -1.41
     I
    -1.35
     Otras
    -1.32
    anın
    -1.30
    ütün
    -1.26
    .
    -1.25
    adır
    -1.24
     Autres
    -1.19
     otorg
    -1.18
    Jeśli
    -1.16
    POSITIVE LOGITS
    urezza
    1.41
    }}$
    1.34
    ixos
    1.34
    의
    1.28
    preneurship
    1.28
    /.../
    1.28
    ur
    1.27
     slike
    1.26
     timur
    1.26
    omorphism
    1.26
    Activations Density 0.024%

    No Known Activations